meta-board-and-investor-reporting
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as 'Claims, assumptions, and supporting evidence' and 'Board And Investor Reporting brief' from various providers. This ingestion of untrusted data into the agent context represents a potential attack surface for indirect prompt injection. * Ingestion points: Defined in the 'Required Inputs' section of SKILL.md, which includes external claims, operating records, and research notes. * Boundary markers: The skill instructions do not specify the use of delimiters or instructions to ignore embedded commands within the interpolated data. * Capability inventory: Analysis of the skill and its references indicates no high-risk capabilities such as arbitrary command execution (eval/exec), file system writes, or network operations. * Sanitization: There is no evidence of escaping, validation, or filtering of the external content prior to processing.
Audit Metadata